Instructions to use janhq/Jan-v1-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use janhq/Jan-v1-4B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="janhq/Jan-v1-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("janhq/Jan-v1-4B")
model = AutoModelForCausalLM.from_pretrained("janhq/Jan-v1-4B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use janhq/Jan-v1-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "janhq/Jan-v1-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "janhq/Jan-v1-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/janhq/Jan-v1-4B

SGLang

How to use janhq/Jan-v1-4B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "janhq/Jan-v1-4B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "janhq/Jan-v1-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "janhq/Jan-v1-4B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "janhq/Jan-v1-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use janhq/Jan-v1-4B with Docker Model Runner:
```
docker model run hf.co/janhq/Jan-v1-4B
```

johnucm commited on Aug 20, 2025

Commit

f657f4e

verified ·

1 Parent(s): 9968e1d

Add `do_sample`attr in generation_config

Browse files

Since `temperature`, `top_k` etc are listed in this file, the `do_sample = true` should also be added. The default value for `do_sample` is false for transformers. Otherwise `GenerationConfig.save_pretrained()` will raise error, e.g.:

```
File "/opt/conda/envs/py310/lib/python3.10/site-packages/transformers/generation/configuration_utils.py", line 837, in save_pretrained
raise ValueError(str(exc) + "\n\nFix these issues to save the configuration.")
ValueError: GenerationConfig is invalid:
- `temperature`: `do_sample` is set to `False`. However, `temperature` is set to `0.6` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `temperature`.
- `top_p`: `do_sample` is set to `False`. However, `top_p` is set to `0.95` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`.
- `min_p`: `do_sample` is set to `False`. However, `min_p` is set to `0.0` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `min_p`.
- `top_k`: `do_sample` is set to `False`. However, `top_k` is set to `20` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_k`.
If you're using a pretrained model, note that some of these attributes may be set through the model's `generation_config.json` file.

Fix these issues to save the configuration.
```

Files changed (1) hide show

generation_config.json +1 -0

generation_config.json CHANGED Viewed

@@ -4,6 +4,7 @@
   "eos_token_id": 151645,
   "transformers_version": "4.52.4",
   "use_cache": false,
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,

   "eos_token_id": 151645,
   "transformers_version": "4.52.4",
   "use_cache": false,
+  "do_sample": true,
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,